zackify

You guys should steal the ideas I had in mind and partially implemented on https://github.com/zackify/revect

Similar to you I saw a lot of bloated projects out there. Mine is 90mb container.

I want to do what your project does but in addition have extensions for every day apps that index into a db.

Your private database for all ai interactions.

I also have a cloud version using the mcp auth spec, but it’s all for fun and probably not worth releasing.

Do you have any plans to do further use cases such as this?

Honestly I think I happened to be on godaddy like 12 years ago looking for a domain and saw it was coming soon. And then I stayed up and tried to get a domain haha

My favorite is my first name .codes

Got it the night before .codes released and have had others try to buy it off me a few times. Never!

This is why I made revect. I even have an obsidian plugin in progress.

The goal to index your obsidian and also persist anything from llm chats, and browsing history.

To your own sqlite database so you can still own your data across providers.

I’m sure someone with much more time than me will win with a better version of it

https://github.com/zackify/revect

Imagine complaining that a language has so many users and projects so it sucks.

Exactly, bun is killer. The test runner is extremely fast.

I can build apps with 1-5 total dependencies and everything just works, and works incredibly fast.

That’s why everyone should be using bun.sh

I use their official dev container config and limit access to a small list of domains too

I would use wispr flow or these other whisper voice to text tools that use ai to be even better

the $100/mo plan is more than enough i never get fully limited

Yes I do the same thing, except I usually just say alright push this up now and it handles it

Oauth isn’t that complicated. It’s not a surprise to see an llm build out from the spec. Honestly I was playing around writing a low level implementation recently just for fun as I built out my first oauth mcp server.

Haha great as in surprisingly good at some simple things that nothing has been able to do locally for me.

The 1 minute first token sucks and has me dreaming for the day of 3-4x the bandwidth

On lm studio I was using mlx

This is specifically why I use LM studio and paid for 128gb on my MacBook.

I kept devstral in memory 15gb~ always since I have so much extra.

I can’t wait for a few years from now where I can have triple the memory bandwidth at this size ram

It does an oauth redirect flow and the client stores the access token and sends it with requests after.

I have built a couple using the spec from a month ago. It works alright.

A lot of bad decisions are in the official implementations. For instance not using native Request / Response types in node, so you’re forced to write a bunch of garbage code to convert it, or install express just to use an mcp server.

If I had the time I’d really make my own mcp implementation in typescript at least.

I find most of the implementations to be so over engineered and abstracted on what could be simple function calls on top of the built in language

For simple stuff like a json file that returns the location of your auth routes, you need to add a “middleware”

When in reality you can just make a route and explicitly return that information.

Every piece is some new abstraction it feels vibe coded.

Agree with each of these points so much!

That’s why I really like copilot agent and codex right now.

Even more parallel stuff and from my phone when I’m just thinking of ideas.

It’s because MCP return types are so basic. It’s text. Or image. Or one other type in the protocol I forget.

It’s not well thought out. I’ve been building one with the new auth spec and their official code and tooling is really lacking.

It could have been so much simpler and straight forward by now.

Instead you have 3 different server types and one is deprecated already (SSE) it’s almost funny

M4 max 128gb ram.

LM studio MLX with full 128k context.

It works well but has a long 1 minute initial prompt processing time.

I wouldn’t buy a laptop for this, I would wait for the new AMD 32gb gpu coming out.

If you want a laptop I even consider my m4 max too slow to use more than just here or there.

It melts if you run this and battery goes down asap. Have to use it docked for full speed really

Ollama breaks for me. If I manually set the context higher. The next api call from clone resets it back.

And ollama keeps taking it out of memory every 4 minutes.

LM studio with MLX on Mac is performing perfectly and I can keep it in my ram indefinitely.

Ollama keep alive is broken as a new rest api call resets it after. I’m surprised it’s this glitched with longer running calls and custom context length.

I used devstral today with cline and open hands. Worked great in both.

About 1 minute initial prompt processing time on an m4 max

Using LM studio because the ollama api breaks if you set the context to 128k.

I thought this was another vercel shill, and cheating up the hackernews ranks LOL

But I tried it today and it’s pretty nice. A few bugs with user creation and custom fields with the beta oauth2 plugin. But overall very solid abstraction that will save lots of time.

Google sign in was a breeze too.

The migrations do not pick up nullable being true for custom fields though, and I see someone else already reported this.

Direct oauth registration works, most everything I need is here!

It seems right now the rules are more clear about if you mention or link out, it’s ok. So that’s why.

We should geofence it to US yeah.

We are thinking of sending a push notification with a discount to pay on web and cancel

Crazy. I thought hackernews didn’t care because this happened yesterday and I never saw anything!

We’re updating our app in a couple days this will save a LOT of money.

We will kick users out to web and pass a JWT in the url with a short lifespan to log the user in on web and then prompt for Apple Pay or credit card. Then a link back to our app’s deep link

Completely agree. Surprised it has to many upvotes when it ends with a “fix” telling you to make useStates that rely on localstorage when you’re doing SSR

I guess what makes this different than EG4’s all in one inverter plus a 5kwh server rack battery, is the integration of software and hardware.

I think you have a great shot at being successful. Because the cheaper options, software isn’t great or fully integrated with the hardware.

These systems are a fraction of the cost of powerwall though.

I learned a lot about the DIY side of this from Will Prose on YouTube. It’s amazing how much markup Tesla has on top of LFP batteries.

Cline over everything for me

Same, that’s kind of funny actually

Yeah lifepo4 will not combust badly. Look up will prose on YouTube he does a lot of tests

The reliability is very very bad. It was really insane that 2 times in the past few months the main dashboard was down as I’m demoing something. Not to mention the deploy outages and almost daily some random thing was unavailable or delayed.

I had to leave a few months ago after the price raises and how many times my boss saw some issue in the project I had with them.

They also deprecated and removed their sqlite backup service. Back to GCP and not worrying about so many outages now.

That’s why you gotta run graphene